用7条规则让大模型输出更像机器，减少人类错觉。
Breaking the Illusion of Identity in LLM Tooling
- 设计7条语言规则，针对性抑制模型的拟人化表达
- 对话中拟人标记减少97%以上，输出长度缩短近半
- 无需修改模型，配置文件即可部署，适合工具链集成
大型语言模型在研发工具链中生成的内容常引发使用者对其具备自主性和理解力的错觉，导致验证行为减弱和信任失准。现有方法无法提供系统性、可部署的输出约束方案。本文提出七条面向输出端的规则，针对已知的语言机制，并通过实证验证。在780次双轮对话（30项任务，13次重复，共1560次API调用）中，拟人化标记从1233处降至33处（降幅超97%，p<0.001），输出词数减少49%，且经由AnthroScore验证，输出倾向机器语调（-1.94对比-0.96，p<0.001）。规则以配置文件形式实现，无需模型修改，验证仅使用单一模型（Claude Sonnet 4）。受限于未评估约束后输出质量，该机制具有向其他领域扩展的潜力。
原文摘要 · Abstract (English)
Large language models (LLMs) in research and development toolchains produce output that triggers attribution of agency and understanding -- a cognitive illusion that degrades verification behavior and trust calibration. No existing mitigation provides a systematic, deployable constraint set for output register. This paper proposes seven output-side rules, each targeting a documented linguistic mechanism, and validates them empirically. In 780 two-turn conversations (constrained vs. default register, 30 tasks, 13 replicates, 1560 API calls), anthropomorphic markers dropped from 1233 to 33 (>97% reduction, p < 0.001), outputs were 49% shorter by word count, and adapted AnthroScore confirmed the shift toward machine register (-1.94 vs. -0.96, p < 0.001). The rules are implemented as a configuration-file system prompt requiring no model modification; validation uses a single model (Claude Sonnet 4). Output quality under the constrained register was not evaluated. The mechanism is extensible to other domains.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。